{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T23:54:47Z","timestamp":1768434887338,"version":"3.49.0"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:p>Morphological changes of the choroid have been proved to be associated with the occurrence and pathological mechanism of many ophthalmic diseases. Optical Coherence Tomography (OCT) is a non-invasive technique for imaging of ocular biological tissues, that can reveal the structure of the retinal and choroidal layers in micron-scale resolution. However, unlike the retinal layer, the interface between the choroidal layer and the sclera is ambiguous in OCT, which makes it difficult for ophthalmologists to identify with certainty. In this paper, we propose a novel boundary-enhanced encoder-decoder architecture for choroid segmentation in retinal OCT images, in which a Boundary Enhancement Module (BEM) forms the backbone of each encoder-decoder layer. The BEM consists of three parallel branches: 1) a Feature Extraction Branch (FEB) to obtain feature maps with different receptive fields; 2) a Channel Enhancement Branch (CEB) to extract the boundary information of different channels; and 3) a Boundary Activation Branch (BAB) to enhance the boundary information <jats:italic>via<\/jats:italic> a novel activation function. In addition, in order to incorporate expert knowledge into the segmentation network, soft key point maps are generated on the choroidal boundary, and are combined with the predicted images to facilitate precise choroidal boundary segmentation. In order to validate the effectiveness and superiority of the proposed method, both qualitative and quantitative evaluations are employed on three retinal OCT datasets for choroid segmentation. The experimental results demonstrate that the proposed method yields better choroid segmentation performance than other deep learning approaches. Moreover, both 2D and 3D features are extracted for statistical analysis from normal and highly myopic subjects based on the choroid segmentation results, which is helpful in revealing the pathology of high myopia. Code is available at <jats:ext-link>https:\/\/github.com\/iMED-Lab\/Choroid-segmentation<\/jats:ext-link>.<\/jats:p>","DOI":"10.3389\/fcell.2022.1060241","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:00:02Z","timestamp":1668067202000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Choroidal layer segmentation in OCT images by a boundary enhancement network"],"prefix":"10.3389","volume":"10","author":[{"given":"Wenjun","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaying","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifeng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhui","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"100829","DOI":"10.1016\/j.preteyeres.2020.100829","article-title":"Exploring choroidal angioarchitecture in health and disease using choroidal vascularity index","volume":"77","author":"Agrawal","year":"2020","journal-title":"Prog. Retin. Eye Res."},{"key":"B2","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B3","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1016\/j.ophtha.2012.06.065","article-title":"Choroidal volume variations with age, axial length, and sex in healthy subjects: A three-dimensional analysis","volume":"119","author":"Barteselli","year":"2012","journal-title":"Ophthalmology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1038\/sj.eye.6701934","article-title":"Prevalence of blindness and low vision in an Italian population: A comparison with other European studies","volume":"20","author":"Cedrone","year":"2006","journal-title":"Eye"},{"key":"B5","first-page":"1966","article-title":"Perceptual-assisted adversarial adaptation for choroid segmentation in optical coherence tomography","author":"Chai","year":"2020"},{"key":"B6","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1167\/tvst.11.2.38","article-title":"Application of artificial intelligence and deep learning for choroid segmentation in myopia","volume":"11","author":"Chen","year":"2022","journal-title":"Transl. Vis. Sci. Technol."},{"key":"B7","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"B8","doi-asserted-by":"publisher","first-page":"8974","DOI":"10.1364\/OE.23.008974","article-title":"Automated choroid segmentation based on gradual intensity distance in hd-oct images","volume":"23","author":"Chen","year":"2015","journal-title":"Opt. Express"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2608","DOI":"10.1167\/iovs.13-13595","article-title":"Changes in choroidal thickness after trabeculectomy in primary angle closure glaucoma","volume":"55","author":"Chen","year":"2014","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1364\/oe.11.002183","article-title":"Sensitivity advantage of swept source and Fourier domain optical coherence tomography","volume":"11","author":"Choma","year":"2003","journal-title":"Opt. Express"},{"key":"B11","doi-asserted-by":"publisher","first-page":"479268","DOI":"10.1155\/2014\/479268","article-title":"Segmentation of choroidal boundary in enhanced depth imaging octs using a multiresolution texture based modeling in graph cuts","volume":"2014","author":"Danesh","year":"2014","journal-title":"Comput. Math. Methods Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"36924","DOI":"10.1109\/access.2021.3062904","article-title":"Document image binarization with stroke boundary feature guided network","volume":"9","author":"Dang","year":"2021","journal-title":"IEEE Access"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"Ce-net: Context encoder network for 2d medical image segmentation","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B14","doi-asserted-by":"publisher","first-page":"123702","DOI":"10.1117\/1.JBO.25.12.123702","article-title":"High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning","volume":"25","author":"Hao","year":"2020","journal-title":"J. Biomed. Opt."},{"key":"B15","doi-asserted-by":"publisher","first-page":"8882801","DOI":"10.1155\/2021\/8882801","article-title":"Choroid segmentation of retinal OCT images based on CNN classifier and l2-lq fitter","volume":"2021","author":"He","year":"2021","journal-title":"Comput. Math. Methods Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1167\/iovs.12-10578","article-title":"Semiautomated segmentation of the choroid in spectral-domain optical coherence tomography volume scans","volume":"54","author":"Hu","year":"2013","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1126\/science.1957169","article-title":"Optical coherence tomography","volume":"254","author":"Huang","year":"1991","journal-title":"science"},{"key":"B18","doi-asserted-by":"publisher","first-page":"3378","DOI":"10.1167\/iovs.12-11503","article-title":"Changes in choroidal thickness in relation to the severity of retinopathy and macular edema in type 2 diabetic patients","volume":"54","author":"Kim","year":"2013","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"B19","first-page":"4817","article-title":"Structure boundary preserving segmentation for medical image with ambiguous boundary","author":"Lee","year":"2020"},{"key":"B20","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"B21","first-page":"1641","article-title":"Deep learning with skip connection attention for choroid layer segmentation in oct images","author":"Mao","year":"2020"},{"key":"B22","doi-asserted-by":"publisher","first-page":"3058","DOI":"10.1038\/s41598-019-39795-x","article-title":"Automatic choroid layer segmentation from optical coherence tomography images using deep learning","volume":"9","author":"Masood","year":"2019","journal-title":"Sci. Rep."},{"key":"B23","doi-asserted-by":"publisher","first-page":"42112","DOI":"10.1038\/srep42112","article-title":"Open-source algorithm for automatic choroid segmentation of oct volume reconstructions","volume":"7","author":"Mazzaferri","year":"2017","journal-title":"Sci. Rep."},{"key":"B24","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1080\/08820538.2017.1307423","article-title":"Evaluation of choroidal and retinal thickness changes in Parkinson\u2019s disease using spectral domain optical coherence tomography","volume":"33","author":"Moschos","year":"2018","journal-title":"Seminars Ophthalmol."},{"key":"B25","first-page":"721","article-title":"Cs-Net: channel and spatial attention network for curvilinear structure segmentation","author":"Mou","year":"2019"},{"key":"B26","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.preteyeres.2009.12.002","article-title":"The multifunctional choroid","volume":"29","author":"Nickla","year":"2010","journal-title":"Prog. Retin. Eye Res."},{"key":"B27","doi-asserted-by":"publisher","first-page":"44","DOI":"10.4102\/aveh.v64i2.214","article-title":"Prevalence and causes of low vision and blindness worldwide","volume":"64","author":"Oduntan","year":"2005","journal-title":"Afr. Vis. eye health"},{"key":"B28","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019"},{"key":"B29","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1111\/cxo.12862","article-title":"Choroidal changes in human myopia: Insights from optical coherence tomography imaging","volume":"102","author":"Read","year":"2019","journal-title":"Clin. Exp. Optom."},{"key":"B30","first-page":"563","volume-title":"Choroidal thickness in patients with diabetic retinopathy analyzed by spectral-domain optical coherence tomography","author":"Regatieri","year":"2012"},{"key":"B31","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B32","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1080\/02713683.2017.1370116","article-title":"Retinal and choroidal changes in patients with Parkinson\u2019s disease detected by swept-source optical coherence tomography","volume":"43","author":"Satue","year":"2018","journal-title":"Curr. Eye Res."},{"key":"B33","doi-asserted-by":"publisher","first-page":"e133","DOI":"10.3928\/23258160-20190503-13","article-title":"Choriocapillary blood flow in myopic subjects measured with oct angiography","volume":"50","author":"Scherm","year":"2019","journal-title":"Ophthalmic Surg. Lasers Imaging Retina"},{"key":"B34","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"B35","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.survophthal.2018.11.002","article-title":"Choroidal imaging biomarkers","volume":"64","author":"Singh","year":"2019","journal-title":"Surv. Ophthalmol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.neucom.2017.01.023","article-title":"Choroid segmentation from optical coherence tomography with graph-edge weights learned from deep convolutional neural networks","volume":"237","author":"Sui","year":"2017","journal-title":"Neurocomputing"},{"key":"B37","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1364\/BOE.4.000397","article-title":"Automatic segmentation of the choroid in enhanced depth imaging optical coherence tomography images","volume":"4","author":"Tian","year":"2013","journal-title":"Biomed. Opt. Express"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1694","DOI":"10.1109\/JBHI.2017.2675382","article-title":"Automatic choroidal layer segmentation using markov random field and level set method","volume":"21","author":"Wang","year":"2017","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1109\/TPAMI.2018.2840695","article-title":"Deepigeos: A deep interactive geodesic framework for medical image segmentation","volume":"41","author":"Wang","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B40","first-page":"206","article-title":"Boundary-aware transformers for skin lesion segmentation","author":"Wang","year":"2021"},{"key":"B41","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s12886-015-0059-2","article-title":"Choroidal thickness and high myopia: A cross-sectional study and meta-analysis","volume":"15","author":"Wang","year":"2015","journal-title":"BMC Ophthalmol."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2021.3126704","article-title":"A concentric loop convolutional neural network for manual delineation level building boundary segmentation from remote sensing images","volume":"60","author":"Wei","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B43","doi-asserted-by":"publisher","first-page":"S75","DOI":"10.3928\/15428877-20110627-07","article-title":"Enhanced depth imaging optical coherence tomography","volume":"42","author":"Wong","year":"2011","journal-title":"Ophthalmic Surg. Lasers Imaging"},{"key":"B44","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1097\/APO.0000000000000234","article-title":"Epidemiology of pathologic myopia in Asia and worldwide","volume":"5","author":"Wong","year":"2016","journal-title":"Asia. Pac. J. Ophthalmol."},{"key":"B45","doi-asserted-by":"publisher","first-page":"5880","DOI":"10.1109\/TIP.2018.2860255","article-title":"Automatic segmentation of retinal layer in oct images with choroidal neovascularization","volume":"27","author":"Xiang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03723-w","article-title":"Automatic choroid layer segmentation in oct images via context efficient adaptive network","author":"Yan","year":"2022","journal-title":"Appl. Intell. (Dordr)."},{"key":"B47","doi-asserted-by":"publisher","first-page":"S6","DOI":"10.2144\/000112090","article-title":"Spectral domain optical coherence tomography: A better oct imaging strategy","volume":"39","author":"Yaqoob","year":"2005","journal-title":"Biotechniques"},{"key":"B48","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1016\/j.ajo.2014.12.010","article-title":"Relationship of central choroidal thickness with age-related macular degeneration status","volume":"159","author":"Yiu","year":"2015","journal-title":"Am. J. Ophthalmol."},{"key":"B49","volume-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015"},{"key":"B50","doi-asserted-by":"publisher","first-page":"106161","DOI":"10.1016\/j.compbiomed.2022.106161","article-title":"Fbcu-net: A fine-grained context modeling network using boundary semantic features for medical image segmentation","volume":"150","author":"Yu","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B51","doi-asserted-by":"publisher","first-page":"3408","DOI":"10.1109\/JBHI.2020.3023144","article-title":"Automatic segmentation and visualization of choroid in oct with knowledge infused deep learning","volume":"24","author":"Zhang","year":"2020","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B52","doi-asserted-by":"publisher","first-page":"7510","DOI":"10.1167\/iovs.12-10311","article-title":"Automated segmentation of the choroid from clinical sd-oct","volume":"53","author":"Zhang","year":"2012","journal-title":"Investig. Ophthalmol. Vis. Sci."}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2022.1060241\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:00:04Z","timestamp":1668067204000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2022.1060241\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":52,"alternative-id":["10.3389\/fcell.2022.1060241"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2022.1060241","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,10]]},"article-number":"1060241"}}